INDEX

Explanations

terms and concepts related to scientific analysis and measurement in research contexts

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

oa̍t

-0.66

ChildIndex

-0.63

 vroeger

-0.55

 short

-0.54

featureID

-0.53

short

-0.50

multer

-0.49

 altijd

-0.49

 siempre

-0.48

 ever

-0.48

POSITIVE LOGITS

pushFollow

0.58

__":

0.57

 BoxFit

0.57

 invokingState

0.55

 BrowserModule

0.55

ʁ

0.54

为例

0.53

нгредієнти

0.51

requisites

0.51

 الحره

0.51

Activations Density 1.988%

terms and concepts related to scientific analysis and measurement in research contexts

No Comments

No Known Activations